Skip to content

Conversation

@igchor
Copy link
Contributor

@igchor igchor commented Nov 1, 2024

Add extra param: ur_device_handle_t

It is necessary to implement this function on L0 for kernels that are build for multiple devices. Right now, the implementation only works when the kernel is created from a native handle.

Ref: #2262

@igchor igchor requested review from a team as code owners November 1, 2024 19:02
@igchor igchor requested a review from jchlanda November 1, 2024 19:02
@igchor igchor marked this pull request as draft November 1, 2024 19:04
@github-actions github-actions bot added loader Loader related feature/bug specification Changes or additions to the specification experimental Experimental feature additions/changes/specification level-zero L0 adapter specific issues cuda CUDA adapter specific issues hip HIP adapter specific issues labels Nov 1, 2024
@igchor
Copy link
Contributor Author

igchor commented Nov 1, 2024

Testing PR to intel/llvm: intel/llvm#15966

@igchor igchor requested a review from nrspruit November 1, 2024 23:08
Copy link
Contributor

@jchlanda jchlanda left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

CUDA/HIP 👍

@igchor igchor marked this pull request as ready for review November 4, 2024 16:03
Copy link
Contributor

@nrspruit nrspruit left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM for L0

@pbalcer
Copy link
Contributor

pbalcer commented Dec 13, 2024

this needs rebasing.

@oneapi-src/unified-runtime-opencl-write please review

Add extra param: ur_device_handle_t

It is necessary to implement this function on L0 for
kernels that are build for multiple devices. Right now,
the implementation only works when the kernel is created
from a native handle.

Ref: oneapi-src#2262
@igchor
Copy link
Contributor Author

igchor commented Dec 13, 2024

this needs rebasing.

@oneapi-src/unified-runtime-opencl-write please review

Done.

@github-actions github-actions bot added the opencl OpenCL adapter specific issues label Dec 13, 2024
@pbalcer
Copy link
Contributor

pbalcer commented Dec 16, 2024

v2 tests failed, but that doesn't seem related.
This is nearly ready to merge, but you will need to undraft your intel/llvm PR and get approval from llvm-reviewers-runtime.

@igchor
Copy link
Contributor Author

igchor commented Dec 17, 2024

v2 tests failed, but that doesn't seem related. This is nearly ready to merge, but you will need to undraft your intel/llvm PR and get approval from llvm-reviewers-runtime.

intel/llvm#15966 is approved.

@kbenzie kbenzie added the ready to merge Added to PR's which are ready to merge label Dec 18, 2024
@martygrant martygrant merged commit ea0f3a1 into oneapi-src:main Dec 19, 2024
69 of 73 checks passed
martygrant added a commit to intel/llvm that referenced this pull request Dec 19, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

cuda CUDA adapter specific issues experimental Experimental feature additions/changes/specification hip HIP adapter specific issues level-zero L0 adapter specific issues loader Loader related feature/bug opencl OpenCL adapter specific issues ready to merge Added to PR's which are ready to merge specification Changes or additions to the specification

Projects

None yet

Development

Successfully merging this pull request may close these issues.

8 participants